Finish the references implementation for the extraction module and update roadmap documentation

This commit is contained in:
2026-07-05 10:53:16 -05:00
parent be6803ffa1
commit a516944086
13 changed files with 280 additions and 562 deletions

View File

@@ -135,6 +135,9 @@ func ResolvePipeline(profile PipelineProfile, options ResolveOptions, catalog Mo
if len(selectedLaneIDs) == 0 {
return ResolvedPipeline{}, fmt.Errorf("pipeline %q must select at least one artifact lane", pipelineID)
}
if err := validatePipelineReferenceDefaults(pipelineID, profile.References, lanesByID, catalog); err != nil {
return ResolvedPipeline{}, err
}
resolved := ResolvedPipeline{
ID: pipelineID,
@@ -238,6 +241,44 @@ func resolveArtifactLane(
return lane, capabilities, nil
}
func validatePipelineReferenceDefaults(
pipelineID string,
pipelineReferences map[string]string,
lanesByID map[string]ArtifactLaneProfile,
catalog ModuleCatalog,
) error {
normalizedPipelineReferences, err := normalizedReferenceMap(pipelineReferences, fmt.Sprintf("pipeline %q reference slot", pipelineID))
if err != nil {
return err
}
if len(normalizedPipelineReferences) == 0 {
return nil
}
declaredByAnyLane := make(map[string]struct{}, len(normalizedPipelineReferences))
for _, laneID := range sortedArtifactLaneProfileKeys(lanesByID) {
laneProfile := lanesByID[laneID]
extract := resolveBinding(laneProfile.Extract, "")
if extract.Module == "" {
return fmt.Errorf("pipeline %q lane %q extract module must not be empty", pipelineID, laneID)
}
extractSpec, err := extractorSpec(catalog, extract.Module)
if err != nil {
return moduleLookupError(pipelineID, laneID, StageExtract, extract.Module, err)
}
for _, slot := range extractSpec.ReferenceSlots {
declaredByAnyLane[slot.Name] = struct{}{}
}
}
for _, slotName := range sortedStringMapKeys(normalizedPipelineReferences) {
if _, ok := declaredByAnyLane[slotName]; !ok {
return fmt.Errorf("pipeline %q reference slot %q is not declared by any artifact lane", pipelineID, slotName)
}
}
return nil
}
func resolveReferenceBindings(
pipelineID string,
laneID string,
@@ -370,6 +411,18 @@ func normalizedReferenceMap(values map[string]string, keyName string) (map[strin
return out, nil
}
func sortedArtifactLaneProfileKeys(values map[string]ArtifactLaneProfile) []string {
if len(values) == 0 {
return nil
}
keys := make([]string, 0, len(values))
for key := range values {
keys = append(keys, key)
}
sort.Strings(keys)
return keys
}
func sortedStringMapKeys(values map[string]string) []string {
if len(values) == 0 {
return nil

View File

@@ -129,8 +129,7 @@ func TestResolvePipelineSelectsOnlyRequestedLanes(t *testing.T) {
func TestResolvePipelineAppliesReferenceBindings(t *testing.T) {
profile := multiLaneProfile()
profile.References = map[string]string{
" roster ": " ./shared-roster.yml ",
"unclaimed": "./ignored.yml",
" roster ": " ./shared-roster.yml ",
}
lane := profile.Artifacts["events"]
lane.References = map[string]string{
@@ -168,6 +167,39 @@ func TestResolvePipelineAppliesReferenceBindings(t *testing.T) {
}
}
func TestResolvePipelineAllowsPipelineReferenceDeclaredOnlyByUnselectedLane(t *testing.T) {
profile := multiLaneProfile()
profile.References = map[string]string{"notes_context": "./notes.md"}
catalog := newProfileCatalogWithOverride(t, ModuleSpec{
Key: "note-extractor",
Stage: StageExtract,
Requires: []string{"chunk"},
Provides: []string{"candidate"},
ReferenceSlots: []contracts.ReferenceSlot{
{Name: "notes_context"},
},
})
resolved, err := ResolvePipeline(profile, ResolveOptions{Only: []string{"events"}}, catalog)
if err != nil {
t.Fatalf("ResolvePipeline() error = %v, want nil", err)
}
if refs := resolved.ArtifactLanes[0].References; len(refs) != 0 {
t.Fatalf("selected lane references = %#v, want none", refs)
}
}
func TestResolvePipelineRejectsPipelineReferenceNotDeclaredByAnyLane(t *testing.T) {
profile := multiLaneProfile()
profile.References = map[string]string{"missing": "./missing.md"}
_, err := ResolvePipeline(profile, ResolveOptions{Only: []string{"events"}}, newProfileCatalog(t))
if err == nil {
t.Fatal("ResolvePipeline() error = nil, want error")
}
assertErrorContains(t, err, "multi", "reference slot", "missing", "not declared")
}
func TestResolvePipelineRejectsUndeclaredReferenceSlot(t *testing.T) {
profile := baselineProfile()
lane := profile.Artifacts["events"]

View File

@@ -4,6 +4,7 @@ import (
"crypto/sha256"
"encoding/hex"
"fmt"
"mime"
"net/url"
"os"
"path/filepath"
@@ -17,7 +18,8 @@ import (
const (
referenceOriginFile = "file"
referenceMediaType = "text/plain; charset=utf-8"
referenceMediaType = "text/plain"
unknownMediaType = "application/octet-stream"
)
type ReferenceMaterializationOptions struct {
@@ -88,6 +90,10 @@ func materializeLaneReferences(
if !utf8.Valid(content) {
return contracts.ReferenceSet{}, nil, fmt.Errorf("pipeline %q lane %q reference slot %q path %q must be UTF-8 text", pipelineID, lane.ID, slotName, path)
}
mediaType := referenceMediaTypeForPath(path)
if !referenceMediaTypeAccepted(mediaType, slot.AcceptedMediaTypes) {
return contracts.ReferenceSet{}, nil, fmt.Errorf("pipeline %q lane %q reference slot %q path %q media type %q is not accepted", pipelineID, lane.ID, slotName, path, mediaType)
}
if slot.MaxBytes > 0 && int64(len(content)) > slot.MaxBytes {
return contracts.ReferenceSet{}, nil, fmt.Errorf("pipeline %q lane %q reference slot %q path %q is %d bytes, limit %d", pipelineID, lane.ID, slotName, path, len(content), slot.MaxBytes)
}
@@ -101,7 +107,7 @@ func materializeLaneReferences(
item := contracts.ReferenceItem{
SlotName: slotName,
MediaType: referenceMediaType,
MediaType: mediaType,
Content: append([]byte(nil), content...),
Digest: referenceDigest(content),
Origin: contracts.ReferenceOrigin{Type: referenceOriginFile, URI: fileURI(path)},
@@ -116,6 +122,43 @@ func materializeLaneReferences(
return set, warnings, nil
}
func referenceMediaTypeForPath(path string) string {
extension := strings.ToLower(filepath.Ext(path))
mediaType := mime.TypeByExtension(extension)
if strings.TrimSpace(mediaType) == "" {
if extension == ".md" || extension == ".markdown" {
return "text/markdown"
}
return unknownMediaType
}
return canonicalMediaType(mediaType)
}
func referenceMediaTypeAccepted(mediaType string, accepted []string) bool {
if len(accepted) == 0 {
return true
}
mediaType = canonicalMediaType(mediaType)
for _, value := range accepted {
if strings.EqualFold(mediaType, canonicalMediaType(value)) {
return true
}
}
return false
}
func canonicalMediaType(mediaType string) string {
trimmed := strings.TrimSpace(mediaType)
if trimmed == "" {
return ""
}
parsed, _, err := mime.ParseMediaType(trimmed)
if err != nil {
return strings.ToLower(trimmed)
}
return strings.ToLower(parsed)
}
func referencePath(binding ReferenceBinding, options ReferenceMaterializationOptions) (string, error) {
source := strings.TrimSpace(binding.Source)
if source == "" {

View File

@@ -117,6 +117,96 @@ func TestMaterializeReferencesRejectsNonUTF8Content(t *testing.T) {
}
}
func TestMaterializeReferencesAllowsAnyMediaTypeWhenSlotDoesNotRestrictIt(t *testing.T) {
configDir := t.TempDir()
path := filepath.Join(configDir, "roster.reference")
writeReferenceFile(t, path, []byte("plain text"))
resolved := resolvedPipelineWithReference(t, "roster", "roster.reference", contracts.ReferenceBindingSourceConfig, contracts.ReferenceSlot{Name: "roster"})
materialized, _, err := MaterializeReferences(resolved, referenceCatalog(t, []contracts.ReferenceSlot{{Name: "roster"}}), ReferenceMaterializationOptions{
ConfigPath: filepath.Join(configDir, "config.yml"),
})
if err != nil {
t.Fatalf("MaterializeReferences() error = %v, want nil", err)
}
item := materialized.ArtifactLanes[0].ReferenceSet.Slots["roster"].Items[0]
if item.MediaType != unknownMediaType {
t.Fatalf("MediaType = %q, want %q", item.MediaType, unknownMediaType)
}
}
func TestMaterializeReferencesAcceptsDeclaredMarkdownMediaType(t *testing.T) {
configDir := t.TempDir()
path := filepath.Join(configDir, "glossary.md")
writeReferenceFile(t, path, []byte("# Terms\n"))
slot := contracts.ReferenceSlot{Name: "glossary", AcceptedMediaTypes: []string{"text/markdown"}}
resolved := resolvedPipelineWithReference(t, "glossary", "glossary.md", contracts.ReferenceBindingSourceConfig, slot)
materialized, _, err := MaterializeReferences(resolved, referenceCatalog(t, []contracts.ReferenceSlot{slot}), ReferenceMaterializationOptions{
ConfigPath: filepath.Join(configDir, "config.yml"),
})
if err != nil {
t.Fatalf("MaterializeReferences() error = %v, want nil", err)
}
item := materialized.ArtifactLanes[0].ReferenceSet.Slots["glossary"].Items[0]
if item.MediaType != "text/markdown" {
t.Fatalf("MediaType = %q, want text/markdown", item.MediaType)
}
}
func TestMaterializeReferencesAcceptsDeclaredJSONMediaType(t *testing.T) {
configDir := t.TempDir()
path := filepath.Join(configDir, "roster.json")
writeReferenceFile(t, path, []byte(`{"aria":"cleric"}`))
slot := contracts.ReferenceSlot{Name: "roster", AcceptedMediaTypes: []string{"application/json"}}
resolved := resolvedPipelineWithReference(t, "roster", "roster.json", contracts.ReferenceBindingSourceConfig, slot)
materialized, _, err := MaterializeReferences(resolved, referenceCatalog(t, []contracts.ReferenceSlot{slot}), ReferenceMaterializationOptions{
ConfigPath: filepath.Join(configDir, "config.yml"),
})
if err != nil {
t.Fatalf("MaterializeReferences() error = %v, want nil", err)
}
item := materialized.ArtifactLanes[0].ReferenceSet.Slots["roster"].Items[0]
if item.MediaType != "application/json" {
t.Fatalf("MediaType = %q, want application/json", item.MediaType)
}
}
func TestMaterializeReferencesRejectsUnacceptedMediaType(t *testing.T) {
configDir := t.TempDir()
path := filepath.Join(configDir, "roster.json")
writeReferenceFile(t, path, []byte(`{"aria":"cleric"}`))
slot := contracts.ReferenceSlot{Name: "roster", AcceptedMediaTypes: []string{"text/markdown"}}
resolved := resolvedPipelineWithReference(t, "roster", "roster.json", contracts.ReferenceBindingSourceConfig, slot)
_, _, err := MaterializeReferences(resolved, referenceCatalog(t, []contracts.ReferenceSlot{slot}), ReferenceMaterializationOptions{
ConfigPath: filepath.Join(configDir, "config.yml"),
})
if err == nil || !strings.Contains(err.Error(), "media type") || !strings.Contains(err.Error(), "application/json") || !strings.Contains(err.Error(), "roster") {
t.Fatalf("error = %v, want media type rejection", err)
}
}
func TestMaterializeReferencesMatchesAcceptedMediaTypesIgnoringParameters(t *testing.T) {
configDir := t.TempDir()
path := filepath.Join(configDir, "roster.txt")
writeReferenceFile(t, path, []byte("Aria\n"))
slot := contracts.ReferenceSlot{Name: "roster", AcceptedMediaTypes: []string{"text/plain; charset=utf-8"}}
resolved := resolvedPipelineWithReference(t, "roster", "roster.txt", contracts.ReferenceBindingSourceConfig, slot)
materialized, _, err := MaterializeReferences(resolved, referenceCatalog(t, []contracts.ReferenceSlot{slot}), ReferenceMaterializationOptions{
ConfigPath: filepath.Join(configDir, "config.yml"),
})
if err != nil {
t.Fatalf("MaterializeReferences() error = %v, want nil", err)
}
item := materialized.ArtifactLanes[0].ReferenceSet.Slots["roster"].Items[0]
if item.MediaType != referenceMediaType {
t.Fatalf("MediaType = %q, want %q", item.MediaType, referenceMediaType)
}
}
func TestMaterializeReferencesWarnsForEmptyFiles(t *testing.T) {
configDir := t.TempDir()
path := filepath.Join(configDir, "empty.txt")